© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20801
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant complications or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.06
    3:0.18
    4:0.02
    5:0.09
    6:0.01
    7:0.06
    8:0.03
    9:0.02
    10:0.35
    11:0.03
    Negative Logits
    araoh
    -2.16
     survived
    -2.11
    cemic
    -2.04
     Sacrifice
    -2.01
     lifetime
    -1.98
    minimum
    -1.93
     cannot
    -1.91
    ahime
    -1.90
    borne
    -1.89
     Preservation
    -1.87
    POSITIVE LOGITS
     anew
    2.50
     earnest
    2.47
     creeping
    2.45
     inward
    2.45
     gradually
    2.31
     cracks
    2.29
     patterns
    2.23
     suspicions
    2.22
     slowly
    2.20
     explos
    2.16
    Activations Density 0.177%

    No Known Activations